JiangChSo/PFLM

What it does

JiangChSo/PFLM is a public GitHub repository with Jupyter Notebook as its primary reported language. GitHub reports 31 stars and 6 forks at the latest snapshot. Its topics include blockchain, federated-learning, membership, privacy-preserving, privacy-preserving-machine-learning. Read the repository documentation, license and current issues before using the software.

Privacy-preserving federated learning is distributed machine learning where multiple collaborators train a model through protected gradients. To achieve robustness to users dropping out, existing practical privacy-preserving federated learning schemes are based on (t, N)-threshold secret sharing. Such schemes rely on a strong assumption to guarantee security: the threshold t must be greater than half of the number of users. The assumption is so rigorous that in some scenarios the schemes may not be appropriate. Motivated by the issue, we first introduce membership proof for federated learning, which leverages cryptographic accumulators to gen

GitHub repositories

Stars

31

Stars gained · 7 days

—

Forks

6

Primary language

Jupyter Notebook

Repository license

Not checked

Last code push

9 Jun 2021

Popularity comes from GitHub stars. Seven-day growth appears after a full week of local snapshots; this is our collection, not GitHub’s official trending chart.

Sources & freshness

Imported records link to their sources. An entry is a discovery aid, not an endorsement.